[PATCH v2 06/14] perf mem: Support AUX trace

From: Leo Yan <leo.yan@linaro.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <ak@linux.intel.com>, Ian Rogers <irogers@google.com>,
	Nick Desaulniers <ndesaulniers@google.com>,
	"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>,
	Kemeng Shi <shikemeng@huawei.com>,
	James Clark <james.clark@arm.com>, Wei Li <liwei391@huawei.com>,
	Al Grant <Al.Grant@arm.com>, Will Deacon <will@kernel.org>,
	Mathieu Poirier <mathieu.poirier@linaro.org>,
	Mike Leach <mike.leach@linaro.org>,
	linux-kernel@vger.kernel.org
Cc: Leo Yan <leo.yan@linaro.org>
Subject: [PATCH v2 06/14] perf mem: Support AUX trace
Date: Tue,  1 Sep 2020 09:38:07 +0100	[thread overview]
Message-ID: <20200901083815.13755-7-leo.yan@linaro.org> (raw)
In-Reply-To: <20200901083815.13755-1-leo.yan@linaro.org>

Perf memory profiling doesn't support aux trace data so the tool cannot
receive the synthesized samples from hardware tracing data.  On the
Arm64 platform, though it doesn't support PMU events for memory load and
store, but Armv8's SPE is a good candidate for memory profiling, the
hardware tracer can record memory accessing operations with physical
address and virtual address for different cache levels and it also stats
the memory operations for remote access and TLB.

To allow the perf memory tool to support AUX trace, this patches adds
the aux callbacks for session structure.  It passes the predefined
itrace option to ask the AUX trace decoder to generate memory samples.
This patch also invokes the standard API perf_event__process_attr() to
register sample IDs into evlist.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/builtin-mem.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index b9432ee27754..ded416d68d88 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,6 +7,7 @@
 #include "perf.h"
 
 #include <subcmd/parse-options.h>
+#include "util/auxtrace.h"
 #include "util/trace-event.h"
 #include "util/tool.h"
 #include "util/session.h"
@@ -252,6 +253,12 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int report_raw_events(struct perf_mem *mem)
 {
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = true,
+		.mem = true,		/* Memory samples */
+		.default_no_sample = true,
+	};
+
 	struct perf_data data = {
 		.path  = input_name,
 		.mode  = PERF_DATA_MODE_READ,
@@ -264,6 +271,8 @@ static int report_raw_events(struct perf_mem *mem)
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
@@ -397,6 +406,19 @@ parse_mem_ops(const struct option *opt, const char *str, int unset)
 	return ret;
 }
 
+static int process_attr(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct evlist **pevlist)
+{
+	int err;
+
+	err = perf_event__process_attr(tool, event, pevlist);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 int cmd_mem(int argc, const char **argv)
 {
 	struct stat st;
@@ -408,8 +430,12 @@ int cmd_mem(int argc, const char **argv)
 			.comm		= perf_event__process_comm,
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
+			.attr		= process_attr,
 			.build_id	= perf_event__process_build_id,
 			.namespaces	= perf_event__process_namespaces,
+			.auxtrace_info  = perf_event__process_auxtrace_info,
+			.auxtrace       = perf_event__process_auxtrace,
+			.auxtrace_error = perf_event__process_auxtrace_error,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
-- 
2.20.1

